© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 91924
    Prev
    Next
    INDEX
    Explanations

    record

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ver
    -0.61
     "
    -0.57
     records
    -0.57
     vs
    -0.54
     c
    -0.54
     long
    -0.54
     a
    -0.53
     fin
    -0.53
     p
    -0.52
     record
    -0.52
    POSITIVE LOGITS
     myſelf
    1.18
     Efq
    1.16
     Monfieur
    1.14
    <bos>
    1.12
     itſelf
    1.12
     Jefus
    1.09
     Majefty
    1.08
     reaſon
    1.05
     themſelves
    1.01
     pleaſure
    0.99
    Activations Density 0.031%

    No Known Activations